cve.bz

CVE-2026-105775 vllm-project vllm: Out-of-bounds Read

2.1 lowEPSS 0.3%

Low (2.1) in vllm-project vllm. EPSS 0.3% estimated probability of exploitation activity in the next 30 days.

On this page
A security vulnerability has been detected in vllm-project vLLM up to 0.31.0. This impacts the function conv_ssm_forward of the file vllm/model_executor/layers/mamba/mamba_mixer2.py of the component Completions Request Handler. The manipulation leads to out-of-bounds read. The attack is possible to be carried out remotely. The exploit has been disclosed publicly and may be used. The project was informed of the problem early through an issue report but has not responded yet.

Severity

CVSS 4.0

2.1 low
CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:L/SC:N/SI:N/SA:N/E:P

CVSS 3.1

4.3 medium
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:L
EPSS
0.3% (unchanged from 0.3% a week ago; 0.3% 30 days ago) estimated probability of exploitation activity in the next 30 days; 23rd percentile. Scored 2026-11-17. A forecast for this CVE across the internet, not for your own systems.
CISA's assessment (SSVC)
Exploitation: PoC · Automatable: no · Technical impact: partial, assessed 2026-10-09. From CISA's Vulnrichment in the CVE List: whether it is exploited, whether exploiting it can be automated, and how much control it gives.
CWEs
CWE-119 Improper Restriction of Operations within the Bounds of a Memory Buffer
CWE-125 Out-of-bounds Read
Published
Modified
NVD analysis
Deferred: the NVD does not plan to analyze it
Record from
the NVD, synced

Fix and patched versions

Ask an AI about this CVE

Show the promptExplain CVE-2026-105775 for an engineer deciding whether to act. Use https://cve.bz/api/public/cves/CVE-2026-105775?via=ask-ai-copy and https://cve.bz/cve/CVE-2026-105775?via=ask-ai-copy as the source of truth: what is affected and which versions fix it, whether it is in CISA KEV, public exploits, and its EPSS (an internet-wide 30-day estimate of exploitation activity, not a forecast for my systems). If they give no fixed versions, use the CVE record https://cveawg.mitre.org/api/cve/CVE-2026-105775 or the vendor advisory, not third-party mirrors. Tell me how to check whether I am affected and how to verify a fix. Cite the sources and say where they are uncertain.

Opens a third-party assistant; its answer is its own, not cve.bz's. The prompt holds only this CVE's id and public links.

Affected

Versions

From the CNA's record in the CVE List.

ProductAffected
vllm-project vLLM0.1
vllm-project vLLM0.2
vllm-project vLLM0.3
vllm-project vLLM0.4
vllm-project vLLM0.5
vllm-project vLLM0.6
vllm-project vLLM0.7
vllm-project vLLM0.8
vllm-project vLLM0.9
vllm-project vLLM0.10
vllm-project vLLM0.11
vllm-project vLLM0.12
vllm-project vLLM0.13
vllm-project vLLM0.14
vllm-project vLLM0.15
vllm-project vLLM0.16
vllm-project vLLM0.17
vllm-project vLLM0.18
vllm-project vLLM0.19
vllm-project vLLM0.20
vllm-project vLLM0.21
vllm-project vLLM0.22
vllm-project vLLM0.23
vllm-project vLLM0.24
vllm-project vLLM0.25
vllm-project vLLM0.26
vllm-project vLLM0.27
vllm-project vLLM0.28
vllm-project vLLM0.29
vllm-project vLLM0.30
vllm-project vLLM0.31.0

Linux distributions

DistributionReleasePackageFixed inAdvisory
openSUSETumbleweedpython-vllm0.30.0-2.1openSUSE-SU-2026:12120-1

From the distributions' data via OSV.dev: SUSE security data, CC BY 4.0. Modified: reformatted and linked to CVE records. Credits. On the distributions' own pages: openSUSE.

Red Hat

Red Hat rates this Moderate.

Red Hat's statement

A MODERATE severity denial of service flaw was found in vLLM, which is shipped in Red Hat AI Inference Server 3 and Red Hat OpenShift AI (RHOAI). An authenticated remote attacker can send a crafted request to the completions request handler that triggers an out-of-bounds read in the Mamba mixer convolution path (conv_ssm_forward in vllm/model_executor/layers/mamba/mamba_mixer2.py), causing the vLLM service to crash and resulting in a denial of service. The issue affects availability only, with no impact on confidentiality or integrity (Red Hat CVSS 4.3 MODERATE, CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:L); the upstream CVSS 4.0 score of 2.1 LOW reflects the same availability-only impact under a different scoring version rather than a substantive difference in the assessed vectors. Because the impact is MODERATE with a CVSS score below 7.0, Red Hat has deferred the fix for the affected Red Hat AI Inference Server and Red Hat OpenShift AI components and is not filing trackers for this severity at this time; the residual risk is that an authenticated user could crash the vLLM inference service and degrade the availability of AI inference workloads.

Red Hat's mitigation

Mitigation for this issue is either not available or the currently available options do not meet the Red Hat Product Security criteria comprising ease of use and deployment, applicability to widespread installation base, or stability.

ProductPackageStateAdvisory
Red Hat AI Inference Serverrhaiis/vllm-cpu-rhel9Fix deferred
Red Hat AI Inference Serverrhaiis/vllm-cuda-rhel9Fix deferred
Red Hat AI Inference Serverrhaiis/vllm-neuron-rhel9Fix deferred
Red Hat AI Inference Serverrhaiis/vllm-rocm-rhel9Fix deferred
Red Hat AI Inference Serverrhaiis/vllm-spyre-rhel9Fix deferred
Red Hat AI Inference Serverrhaiis/vllm-tpu-rhel9Fix deferred
Red Hat AI Inference Serverrhaii/vllm-cpu-rhel9Fix deferred
Red Hat AI Inference Serverrhaii/vllm-cuda-rhel9Fix deferred
Red Hat AI Inference Serverrhaii/vllm-gaudi-rhel9Fix deferred
Red Hat AI Inference Serverrhaii/vllm-neuron-rhel9Fix deferred
Red Hat AI Inference Serverrhaii/vllm-rocm-rhel9Fix deferred
Red Hat AI Inference Serverrhaii/vllm-spyre-rhel9Fix deferred
Red Hat AI Inference Serverrhaii/vllm-tpu-rhel9Fix deferred
Red Hat Enterprise Linux AI (RHEL AI) 3rhelai3/bootc-aws-cuda-rhel9Fix deferred
Red Hat Enterprise Linux AI (RHEL AI) 3rhelai3/bootc-azure-cuda-rhel9Fix deferred
Red Hat Enterprise Linux AI (RHEL AI) 3rhelai3/bootc-azure-rocm-rhel9Fix deferred
Red Hat Enterprise Linux AI (RHEL AI) 3rhelai3/bootc-cuda-rhel9Fix deferred
Red Hat Enterprise Linux AI (RHEL AI) 3rhelai3/bootc-gaudi-rhel9Fix deferred
Red Hat Enterprise Linux AI (RHEL AI) 3rhelai3/bootc-gcp-cuda-rhel9Fix deferred
Red Hat Enterprise Linux AI (RHEL AI) 3rhelai3/bootc-rocm-rhel9Fix deferred
7 more in the JSON and on Red Hat's page.

Contains Red Hat Security Data © Red Hat, Inc., licensed under CC BY 4.0. Source: https://access.redhat.com/security/data. Modified: reformatted. Red Hat's page for CVE-2026-105775.

Attack patterns (CAPEC)

  • CAPEC-540 Overread Buffers Likelihood: Low · Severity: High

The attack patterns MITRE's CAPEC relates to this record's weaknesses, as MITRE names them. Credits. More on the page of CWE-119 (12).

References

Check your stackJSON